Temporal Coding in Leaky Spiking Neural Networks
AssigneeGoogle Inc.
InventorsJyrki Alakuijala, Iulia-Maria Comsa, Krzysztof Potempa
Life of this patent
Estimating the term…
Loading patent…
AssigneeGoogle Inc.
InventorsJyrki Alakuijala, Iulia-Maria Comsa, Krzysztof Potempa
Estimating the term…
Spiking neural networks that perform temporal encoding for phase-coherent neural computing are provided. In particular, according to an aspect of the present disclosure, a spiking neural network can include one or more spiking neurons that have an activation layer that uses a double exponential function to model a leaky input that an incoming neuron spike provides to a membrane potential of the spiking neuron. The use of the double exponential function in the neuron's temporal transfer function creates a better defined maximum in time. This allows very clearly defined state transitions between “now” and the “future step” to happen without loss of phase coherence.
A computer system comprising:
A computer-implemented method to train a spiking neural network that encodes information in respective spike times associated with a plurality of spiking neurons included in the spiking neural network, the method comprising:
An electronic device that comprises:
(canceled)
Dependencies are inferred from the claim text.